Hugging Face's logo

hivex-research
/
hivex-WRM-PPO-baseline-task-0-difficulty-10

Reinforcement Learning
TensorBoard
ONNX
hivex
hivex-wildfire-resource-management
multi-agent-reinforcement-learning
Eval Results
Model card Files Metrics Community

This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Wildfire Resource Management
Task: 0
Difficulty: 10
Algorithm: PPO
Episode Length: 500
Training max_steps: 450000
Testing max_steps: 45000

Train & Test Scripts
Download the Environment

Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
Reinforcement Learning
loading

Collection including hivex-research/hivex-WRM-PPO-baseline-task-0-difficulty-10

Evaluation results

  • Cumulative Reward on hivex-wildfire-resource-management
    self-reported
    103.69761962890625 +/- 33.62321244800703
  • Collective Performance on hivex-wildfire-resource-management
    self-reported
    55.50396175384522 +/- 22.88109053127101
  • Individual Performance on hivex-wildfire-resource-management
    self-reported
    24.726867961883546 +/- 9.733685238014223
  • Reward for Moving Resources to Neighbours on hivex-wildfire-resource-management
    self-reported
    40.47791290283203 +/- 17.508142474539696
  • Reward for Moving Resources to Self on hivex-wildfire-resource-management
    self-reported
    3.59446302652359 +/- 2.410688145025967
View on Papers With Code